{"id":"https://openalex.org/W4375869387","doi":"https://doi.org/10.1109/icassp49357.2023.10096479","title":"Efficient Intelligibility Evaluation Using Keyword Spotting: A Study on Audio-Visual Speech Enhancement","display_name":"Efficient Intelligibility Evaluation Using Keyword Spotting: A Study on Audio-Visual Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869387","doi":"https://doi.org/10.1109/icassp49357.2023.10096479"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/eb77fff2-ba0d-400d-ae46-0802f0be4587","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,UK","The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019555477","display_name":"Andrea Lorena Aldana Blanco","orcid":"https://orcid.org/0000-0003-2585-5155"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrea Lorena Aldana Blanco","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,UK","The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044666169","display_name":"Ond\u0159ej Klejch","orcid":"https://orcid.org/0000-0001-5495-967X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ondrej Klejch","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,UK","The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,UK","The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019012876"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.8004,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70042116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8840864896774292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8363081216812134},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7880010008811951},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7054383754730225},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6781392097473145},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.661940336227417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5504827499389648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4736810028553009}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8840864896774292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363081216812134},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7880010008811951},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7054383754730225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6781392097473145},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.661940336227417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5504827499389648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4736810028553009},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/eb77fff2-ba0d-400d-ae46-0802f0be4587","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/eb77fff2-ba0d-400d-ae46-0802f0be4587","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini Botinhao, C, Aldana Blanco, A L, Klejch, O & Bell, P 2023, Efficient intelligibility evaluation using keyword spotting : A study on audio-visual speech enhancement. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Institute of Electrical and Electronics Engineers, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10096479","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/eb77fff2-ba0d-400d-ae46-0802f0be4587","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/10096479","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/eb77fff2-ba0d-400d-ae46-0802f0be4587","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/331418110/Efficient_intelligibility_VALENTINI_BOTINHAO_DOA_15022023_AFV_CC_BY.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini Botinhao, C, Aldana Blanco, A L, Klejch, O & Bell, P 2023, Efficient intelligibility evaluation using keyword spotting : A study on audio-visual speech enhancement. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Institute of Electrical and Electronics Engineers, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10096479","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/eb77fff2-ba0d-400d-ae46-0802f0be4587","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/eb77fff2-ba0d-400d-ae46-0802f0be4587","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini Botinhao, C, Aldana Blanco, A L, Klejch, O & Bell, P 2023, Efficient intelligibility evaluation using keyword spotting : A study on audio-visual speech enhancement. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Institute of Electrical and Electronics Engineers, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10096479","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2447866707","display_name":null,"funder_award_id":"EP/T021063/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1521190806","https://openalex.org/W1981527043","https://openalex.org/W2067295501","https://openalex.org/W2068472853","https://openalex.org/W2144404214","https://openalex.org/W2163010125","https://openalex.org/W2604379605","https://openalex.org/W2750452568","https://openalex.org/W2788241093","https://openalex.org/W2964171275","https://openalex.org/W3008400075","https://openalex.org/W3011424113","https://openalex.org/W3020804303","https://openalex.org/W3103318788","https://openalex.org/W3160348851","https://openalex.org/W3165994203","https://openalex.org/W3197832224","https://openalex.org/W3205327997","https://openalex.org/W4231807801","https://openalex.org/W4289665794","https://openalex.org/W4319862437","https://openalex.org/W6667372801","https://openalex.org/W6735927292","https://openalex.org/W6849595638"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W1483316057"],"abstract_inverted_index":{"We":[0,83,96,121],"propose":[1],"a":[2,19,28,46,52,56,93,101,126,138],"new":[3],"method":[4,63,99],"for":[5],"human":[6],"speech":[7,88],"intelligibility":[8,145],"evaluation":[9,91,128],"based":[10],"on":[11,67,85,125],"keyword":[12,135],"spotting.":[13],"In":[14],"this":[15],"method,":[16],"participants":[17],"play":[18],"stimulus":[20],"and":[21,42,55,71,104,140],"select":[22],"the":[23,39,107],"word":[24],"they":[25],"hear":[26],"from":[27,146],"close":[29],"set":[30,48],"of":[31,49,129],"alternatives.":[32],"To":[33],"find":[34],"which":[35],"sentence":[36],"to":[37,75,100,143],"use,":[38],"target":[40],"word,":[41],"alternatives":[43],"we":[44],"mine":[45],"large":[47],"stimuli":[50],"using":[51],"phonetic":[53],"dictionary":[54],"language":[57],"model.":[58],"Unlike":[59],"other":[60],"tests,":[61],"our":[62,98,114],"does":[64],"not":[65],"rely":[66],"specially":[68],"designed":[69],"sentences":[70],"can":[72],"be":[73],"used":[74],"evaluate":[76],"in-the-wild":[77],"material":[78],"such":[79],"as":[80,92],"TED":[81],"talks.":[82],"focus":[84],"audio-visual":[86],"(AV)":[87],"enhancement":[89],"(SE)":[90],"study":[94],"case.":[95],"compared":[97],"transcription":[102],"task":[103,115],"observed":[105],"that":[106,134],"two":[108],"produce":[109],"highly":[110],"correlated":[111],"results,":[112],"albeit":[113],"requiring":[116],"substantially":[117],"less":[118],"participation":[119],"time.":[120],"then":[122],"adopted":[123],"it":[124],"large-scale":[127],"AVSE":[130],"systems.":[131],"Results":[132],"show":[133],"spotting":[136],"is":[137],"suitable":[139],"efficient":[141],"alternative":[142],"assess":[144],"AV":[147],"stimuli.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}